A Coupled Model for Forecasting Spatiotemporal Variability of Regional Drought in the Mu Us Sandy Land Using a Meta-Heuristic Algorithm DOI Creative Commons
Changfu Tong, Hongfei Hou, Hexiang Zheng

и другие.

Land, Год журнала: 2024, Номер 13(11), С. 1731 - 1731

Опубликована: Окт. 22, 2024

Vegetation plays a vital role in terrestrial ecosystems, and droughts driven by rising temperatures pose significant threats to vegetation health. This study investigates the evolution of drought from 2010 2024 introduces deep-learning-based forecasting model for analyzing regional spatial temporal variations drought. Extensive time-series remote-sensing data were utilized, we integrated Temperature–Vegetation Dryness Index (TVDI), Drought Severity (DSI), Evaporation Stress (ESI), Temperature–Vegetation–Precipitation (TVPDI) develop comprehensive methodology extracting characteristics. To mitigate effects non-stationarity on predictive accuracy, propose coupling-enhancement strategy that combines Whale Optimization Algorithm (WOA) with Informer model, enabling more precise long-term variations. Unlike conventional deep-learning models, this approach rapid convergence global search capabilities, utilizing sparse self-attention mechanism improves performance while reducing complexity. The results demonstrate that: (1) compared traditional Transformer test accuracy is improved 43%; (2) WOA–Informer efficiently handles multi-objective extended time series, achieving MAE (Mean Absolute Error) ≤ 0.05, MSE Squared 0.001, MSPE Percentage 0.01, MAPE 5%. research provides advanced tools support restoration efforts.

Язык: Английский

Investigation of Lamb wave modes recognition and acoustic emission source localization for steel plate based on golden jackal optimization VMD parameters and CWT DOI

Shishang Dong,

Jun You,

MOHAMED EL-ATTAOUY

и другие.

Measurement, Год журнала: 2024, Номер unknown, С. 116103 - 116103

Опубликована: Окт. 1, 2024

Язык: Английский

Процитировано

4
Driving analysis and prediction of COD based on frequency division DOI

Mei Li,

Kexing Chen,

Deke Wang

и другие.

Stochastic Environmental Research and Risk Assessment, Год журнала: 2025, Номер unknown

Опубликована: Фев. 20, 2025

Язык: Английский

Процитировано

0
An Optimized Maximum Second-Order Cyclostationary Blind Deconvolution and Bidirectional Long Short-Term Memory Network Model for Rolling Bearing Fault Diagnosis DOI Creative Commons
Jixin Liu, Liwei Deng, Yue Cao

и другие.

Sensors, Год журнала: 2025, Номер 25(5), С. 1495 - 1495

Опубликована: Фев. 28, 2025

To address the challenge of extracting fault features and accurately identifying bearing conditions under strong noisy environments, a rolling failure diagnostic technique is presented that utilizes parameter-optimized maximum second-order cyclostationary blind deconvolution (CYCBD) bidirectional long short-term memory (BiLSTM) networks. Initially, an adaptive golden jackal optimization (GJO) algorithm employed to refine important CYCBD parameters. Subsequently, signals are filtered denoised using optimized CYCBD, producing signal. Ultimately, noise-reduced signal fed into BiLSTM model realize classification faults. The experimental findings demonstrate suggested approach’s noise reduction performance high accuracy. CYCBD–BiLSTM improves accuracy by approximately 9.89% compared with other methods when signal-to-noise ratio (SNR) reaches −9 dB, it can be effectively used for diagnosing faults backgrounds.

Язык: Английский

Процитировано

0
Improved KW entropy: a complexity measurement technique for time series and its application in feature extraction of quay crane gearbox DOI
Chunxia Gu, Juan Bi, Bing Wang

и другие.

Neural Computing and Applications, Год журнала: 2025, Номер unknown

Опубликована: Март 21, 2025

Язык: Английский

Процитировано

0
Study on noise reduction method for bridge temperature signal using adaptive parameter selection and improved wavelet threshold function DOI

Zhongchu Tian,

Jiangyan Wu,

Zujun Zhang

и другие.

Measurement, Год журнала: 2025, Номер unknown, С. 117683 - 117683

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
A deep-transfer-learning fault diagnosis method for gearboxes based on discriminative feature extraction and improved domain adversarial neural networks DOI

Xiaoliang He,

Feng Zhao, Nianyun Song

и другие.

Nondestructive Testing And Evaluation, Год журнала: 2025, Номер unknown, С. 1 - 22

Опубликована: Апрель 23, 2025

Язык: Английский

Процитировано

0
An intelligent fault diagnosis for rotating machine under strong noise based on cross-attention-driven spatial-temporal feature fusion and duplexing time sequence convolution optimization DOI
Mingyue Yu, Yongpeng Li, Guanglei Meng

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 153, С. 110897 - 110897

Опубликована: Апрель 29, 2025

Язык: Английский

Процитировано

0
A Novel Multi-Task Self-Supervised Transfer Learning Framework for Cross-Machine Rolling Bearing Fault Diagnosis DOI Open Access

Lujia Zhao,

Yuling He, De‐Rui Dai

и другие.

Electronics, Год журнала: 2024, Номер 13(23), С. 4622 - 4622

Опубликована: Ноя. 23, 2024

In recent years, intelligent methods based on transfer learning have achieved significant research results in the field of rolling bearing fault diagnosis. However, most studies focus diagnosis scenario under different working conditions same machine. The used for machines problems such as low recognition accuracy and unstable performance. Therefore, a novel multi-task self-supervised framework (MTSTLF) is proposed cross-machine method trained using paradigm, which includes three tasks one task. First, scales masking are designed to generate masked vibration data periodicity intrinsic information signals. Through learning, attention features health enhanced, thereby improving model’s feature expression capability. Secondly, multi-perspective completing tasks. By integrating two types metrics, probability distribution geometric similarity, focuses transferable knowledge from perspectives, enhancing ability accomplishing bearings. Two experimental cases carried out evaluate effectiveness method. Results suggest that effective

Язык: Английский

Процитировано

3
A Coupled Model for Forecasting Spatiotemporal Variability of Regional Drought in the Mu Us Sandy Land Using a Meta-Heuristic Algorithm DOI Creative Commons
Changfu Tong, Hongfei Hou, Hexiang Zheng

и другие.

Land, Год журнала: 2024, Номер 13(11), С. 1731 - 1731

Опубликована: Окт. 22, 2024

Vegetation plays a vital role in terrestrial ecosystems, and droughts driven by rising temperatures pose significant threats to vegetation health. This study investigates the evolution of drought from 2010 2024 introduces deep-learning-based forecasting model for analyzing regional spatial temporal variations drought. Extensive time-series remote-sensing data were utilized, we integrated Temperature–Vegetation Dryness Index (TVDI), Drought Severity (DSI), Evaporation Stress (ESI), Temperature–Vegetation–Precipitation (TVPDI) develop comprehensive methodology extracting characteristics. To mitigate effects non-stationarity on predictive accuracy, propose coupling-enhancement strategy that combines Whale Optimization Algorithm (WOA) with Informer model, enabling more precise long-term variations. Unlike conventional deep-learning models, this approach rapid convergence global search capabilities, utilizing sparse self-attention mechanism improves performance while reducing complexity. The results demonstrate that: (1) compared traditional Transformer test accuracy is improved 43%; (2) WOA–Informer efficiently handles multi-objective extended time series, achieving MAE (Mean Absolute Error) ≤ 0.05, MSE Squared 0.001, MSPE Percentage 0.01, MAPE 5%. research provides advanced tools support restoration efforts.

Язык: Английский

Процитировано

0